paper-with-me

홈 › Papers

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

2022-12-07 · ICCV 2023 1 · Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya Harada

The long-standing theory that a colour-naming system evolves under dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies, including analysing four decades of diachronic data from the Nafaanra language. This inspires us to explore whether machine learning could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette; meanwhile the Palette Branch utilises a key-point detection way to find proper colours in the palette among the whole colour space. By interacting with colour annotation, CQFormer is able to balance both the machine vision accuracy and colour perceptual structure such as distinct and stable colour distribution for discovered colour system. Very interestingly, we even observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining high performance in high-level recognition tasks such as classification and detection. Extensive experiments demonstrate the superior performance of our method with extremely low bit-rate colours, showing potential to integrate into quantisation network to quantities from image to network activation. The source code is available at https://github.com/ryeocthiv/CQFormer

📄 PDF Abstract BibTeX arXiv:2212.03434

Code (1)

ryeocthiv/cqformer 공식 구현 pytorch

Similar Papers 제목 키워드 기반

ganX -- generate artificially new XRF a python library to generate MA-XRF raw data out of RGB images

2023-04-27 · Alessandro Bombini

In this paper we present the first version of ganX -- generate artificially new XRF, a Python library to generate X-ray fluorescence Macro maps (MA-XRF) from a coloured RGB image. To do that, a Monte Carlo method is used…

Generation Of Colors using Bidirectional Long Short Term Memory Networks

2023-11-11 · A. Sinha

Human vision can distinguish between a vast spectrum of colours, estimated to be between 2 to 7 million discernible shades. However, this impressive range does not inherently imply that all these colours have been precis…

Active LearningText-to-Image Generation

Generating a Graph Colouring Heuristic with Deep Q-Learning and Graph Neural Networks

2023-04-08 · George Watkins, Giovanni Montana, Juergen Branke

The graph colouring problem consists of assigning labels, or colours, to the vertices of a graph such that no two adjacent vertices share the same colour. In this work we investigate whether deep reinforcement learning c…

Deep Reinforcement LearningGraph Neural NetworkQ-Learningreinforcement-learning+1

Collaborative Filtering Ensemble for Personalized Name Recommendation

2014-07-16 · Bernat Coma-Puig, Ernesto Diaz-Aviles, Wolfgang Nejdl

Out of thousands of names to choose from, picking the right one for your child is a daunting task. In this work, our objective is to help parents making an informed decision while choosing a name for their baby. We follo…

Collaborative FilteringRecommendation Systems

Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons

2017-09-19 · Arash Akbarinia, C. Alejandro Parraga

Although it seems counter-intuitive, categorical colours do not exist as external physical entities but are very much the product of our brains. Our cortical machinery segments the world and associate objects to specific…